Kilonova MCP

io.github.MilnaOSPublished by GitHub account MilnaOSv0.1.1Updated Oct 24, 2026

Persistent local knowledge for AI coding agents with structured records, search, and DOT context.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Local, file-based knowledge base for AI coding agents: stores project state, decisions and patterns as structured records and loads them back across sessions.

What you can do
  • Load a DOT (Document of Truth) reference document into context, with a table of contents so only needed sections are fetched
  • Search, write and load structured records by topic, entity type and name, merging updates into existing entries
  • List knowledge base topics with record counts and show the field schema for an entity type
  • Report knowledge base size and record counts, and mirror the knowledge base to OneDrive with an optional dry run
When to use it
Useful when working with a coding agent across many sessions on the same projects and you want decisions, conventions and in-flight tasks to persist instead of being re-explained each time. Also fits teams that want a local, schema-defined store of project knowledge without a cloud service.
Requirements
Runs as a local Python process installed from PyPI (pip install kilonova-mcp) and launched via python -m kilonova_mcp. Needs a knowledge base directory, set with the KILONOVA_KB_ROOT environment variable or a platform default. Optional starter schemas and a CLAUDE.md template are copied manually. Desktop only.
Before you install
The assistant can write and update records in the knowledge base, so stored content changes over time; review what gets saved. The backup tool mirrors the knowledge base to OneDrive, which copies local project notes to a third-party cloud service. Knowledge base contents may include internal architecture and decisions, so point KILONOVA_KB_ROOT at a suitable location.

Installation

In SourceWeft

  1. Open Kilonova MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Kilonova MCP

Persistent knowledge base tools for Claude Code.
Claude remembers your projects, decisions, and patterns across sessions — stored on your machine, no cloud required.

Built by AIM Studio · Free · MIT License

The Problem

Every Claude Code session starts cold. You re-explain your project structure, re-describe decisions you made last week, re-state what's in flight. Context burns fast.

The Solution: DOT + KB

Kilonova gives Claude a persistent knowledge base on your local machine. At session start, Claude loads your DOT (Document of Truth) — a compressed, structured reference doc with your project state, active tasks, decisions, and patterns. During the session, Claude writes new discoveries back to the KB. Next session, it's all there.

Session 1: Claude learns your architecture → kb_write saves the decisionSession 2: dot_load → Claude already knows. No recap needed.

Install

bash
pip install kilonova-mcp

Or from source:

bash
git clone https://github.com/MilnaOS/kilonova-mcpcd kilonova-mcppip install -e .

Wire Up Claude Code

Add to ~/.claude/settings.json:

json
{  "mcpServers": {    "kilonova": {      "command": "python",      "args": ["-m", "kilonova_mcp"],      "env": {        "KILONOVA_KB_ROOT": "/path/to/your/kb"      }    }  }}

Copy CLAUDE.md.template to ~/.claude/CLAUDE.md (or append to your existing one).

Quick Start

1. Create your first KB topic:

In Claude Code, just start writing:

mcp__kilonova__kb_write(  topic="claude_context",  entity_type="project_state",  name="my-project",  data={    "name": "my-project",    "status": "active",    "location": "/path/to/project",    "summary": "What this project is",    "next_action": "What to do next"  })

2. Load it next session:

mcp__kilonova__dot_load(topic="claude_context")

3. Search it:

mcp__kilonova__kb_search(topic="claude_context", query="authentication decision")

The DOT Format

A DOT is a plain text file with two sections:

---TOC---1:Projects|1.1:My_Project2:Active_Tasks3:Decisions
---CARDS---
## [1] PROJECTS### [1.1] My ProjectSTATUS: activeNEXT: wire up the auth flow

The TOC lets Claude fetch only the section it needs. Cards hold the actual content.

See example_dot/ for a starter template.

Starter Schema: claude_context

Copy schemas/claude_context/ into your KB directory under <kb_root>/claude_context/schemas/:

Entity typeUse for
project_stateCurrent status, location, next action per project
decisionArchitectural choices with rationale
patternCode conventions, gotchas, file locations
active_taskIn-flight work across sessions
session_noteEnd-of-session summaries

Tools

ToolDescription
dot_load(topic)Load full DOT document into context
kb_search(topic, query)Search records by natural language query
kb_write(topic, entity_type, name, data)Write/update a record (merges with existing)
kb_load(topic, entity_type, name)Load one specific record
kb_topics()List all KB topics and record counts
kb_schema(topic, entity_type?)Show field schema for an entity type
corpus_status(topic)Show KB size and record counts
kb_backup(dry?)Mirror KB to OneDrive

Bring Your Own KB

Kilonova doesn't care what you store. Define your own schemas:

json
// kb/my_topic/schemas/component.json{  "name": {"type": "string", "description": "Component name"},  "file": {"type": "string", "description": "Path to file"},  "purpose": {"type": "string", "description": "What it does"},  "dependencies": {"type": "array", "description": "What it depends on"}}

Then write records to it and search them naturally.

Part of the Kilonova Ecosystem

Kilonova MCP is the free, standalone KB layer extracted from Milna OS — a full BYOK multi-model AI terminal. If you want the whole thing (parallel model legs, distillation engine, web ingestion, local+cloud hybrid inference), check out Milna OS.

MIT License · © AIM Studio

Source: README.md at commit ccb7767

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts